SEAR: Self-Evolving Agentic Robotics
cs.RO, cs.AI, cs.CL
Submitted: 2026-10-13
Updated: 2026-10-13
Comments: 16 pages
Code: https://github.com/Self-Evolving-Agentic-Robotics/SEAR
Project page: https://lilianweng.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Demonstrating specification gaming in reasoning models
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
- CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
- Addressing the Orchestration Gap in Generalist Robots via Physical Agency
- Make Code as Policy Great Again: Frontier Agents Write, Call, and Evolve Robot Tools
- SimEX: Simulation-Integrated Robotics AutoResearch
- Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement
- Learning and Transferring Closed-Loop Robot Software
- RACaP: Agentic Reasoning, Acting, and Coding as Policies for Evolvable Robot Learning
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
- ASPIRE: Agentic /Skills Discovery for Robotics
- RLE-Bench: A Qualifying Exam for Coding Agents as Robot Learning Engineers
- PostTrainBench: Can LLM Agents Automate LLM Post-Training?
- EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics
- Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- What Stops Recursive Self-Improvement in Robotics? Lessons from 123 Rounds of Agentic Skill Discovery
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies